monitor-strategy-run

What problem does it solve?

This Skill eliminates the risk of relying on unvalidated, non-reproducible quant strategy backtest runs that lack proper audit trails, ensuring only trustworthy, compliant research results are used for decision-making.

Core Features & Use Cases

• Run Artifact Validation: Verifies that run directories contain all required audited artifacts and passes schema validation for spec and runtime audit files.
• Automated Audit Execution: Runs reproducibility, research bias, and robustness checks via the open-xquant CLI to flag critical issues like hash mismatches, survivorship risk, or parameter fragility.
• Experiment Logging & Reporting: Registers verified runs to the central experiment log and supports generating structured research reports with full audit context and warning disclosures. Use Case: A quant researcher who just completed a backtest can use this Skill to automatically validate all run artifacts, run all required audits, and generate a compliant research report with all findings documented, without manually running individual CLI commands.

Quick Start

Use the monitor-strategy-run skill to audit the completed backtest run with ID 'run_20240520_001' and generate a full integrity report including all audit and robustness findings.